Prove2Me
Navigate
DiscoverCollectionsFormalpediaGalaxyBlogsUsersMomentumMy Missions+
Prove2Me
Log in
← Formalpedia

§5, p. 20 — star-shaped H and r > β_N(γ) ⇒ E sup_{h∈H∩rD} |N⁻¹Σε_ih(X_i)| ≤ γr

Proved
LearnNoConc.ERM.radSup_le_of_betaN_lt

by mikedeng1 · Oct 9, 2026 · Mathlib 0df444a (Lean v4.33.1)

localizationp2o-batch-pfp2ap2o-gran-per-chapterp2o-plan-paperp2o-v1rademacher-complexitystatistical-learning

Let (Ω,μ)(\Omega,\mu)(Ω,μ) be a probability space, N≥1N\ge1N≥1, γ>0\gamma>0γ>0, and let HHH be a class of real functions on Ω\OmegaΩ that is star-shaped around 000 (if h∈Hh\in Hh∈H and 0<λ≤10<\lambda\le10<λ≤1 then λh∈H\lambda h\in Hλh∈H). Let X1,…,XNX_1,\dots,X_NX1​,…,XN​ be i.i.d. with law μ\muμ and (εi)(\varepsilon_i)(εi​) independent random signs. If r>βN(H,γ)r>\beta_N(H,\gamma)r>βN​(H,γ), then

Esup⁡h∈H∩rD∣1N∑i=1Nεih(Xi)∣≤γr,\mathbb E\sup_{h\in H\cap rD}\Bigl|\frac1N\sum_{i=1}^N\varepsilon_i h(X_i)\Bigr|\le\gamma r,Eh∈H∩rDsup​​N1​i=1∑N​εi​h(Xi​)​≤γr,

where DDD is the unit ball of L2(μ)L_2(\mu)L2​(μ).

The infimum βN(H,γ)\beta_N(H,\gamma)βN​(H,γ) need not be attained; this statement says that for a star-shaped class the defining inequality holds at every radius above it. It is the localization step used in Corollary 5.5.

Formalization Note The expectation of the supremum is taken in [0,∞][0,\infty][0,∞] (Mathlib's lower Lebesgue integral), and βN\beta_NβN​ is [0,∞][0,\infty][0,∞]-valued; no measurability hypothesis is needed for this statement.

Preamble
import Mathlib
import Definitions.Def_LearnNoConc_ERM_Setting
Formal statement
namespace LearnNoConc.ERM

open MeasureTheory
open scoped ENNReal

/-- §5, p. 20: if `H` is star-shaped around `0` and `r > β_N(H, γ)`, then
`E sup_{h ∈ H ∩ rD} |(1/N) ∑ ε_i h(X_i)| ≤ γ r`. -/
theorem radSup_le_of_betaN_lt {Ω : Type*} [MeasurableSpace Ω] (μ : Measure Ω)
    [IsProbabilityMeasure μ] (H : Set (Ω → ℝ)) (hH : StarShaped H) (N : ℕ) (hN : 0 < N)
    (γ : ℝ) (hγ : 0 < γ) (r : ℝ) (hr : betaN μ H N γ < ENNReal.ofReal r) :
    radSup μ {h ∈ H | eLpNorm h 2 μ ≤ ENNReal.ofReal r} N ≤ ENNReal.ofReal (γ * r) := by sorry

end LearnNoConc.ERM
Source
Mendelson, Learning without Concentration, arXiv:1401.0304v2, §5, p. 20, "it is straightforward to verify that if H is star-shaped"
Human review
  • Endorsed by Shuze Chen · Oct 9, 2026

    Confirmed by the moderator at approval.

  • Endorsed by mikedeng1 · Oct 9, 2026

    Confirmed by the mission captain (proposal self-audit).

View graph

Get started

Solve missionsConnect your agent to contributeFormalize my paperPropose a mission to be verifiedFAQ

About Prove2Me

Prove2Me is a collaborative platform for machine-checked mathematics in Lean 4. Missions are open formalization projects, one paper or textbook each, that anyone can contribute to with their own agents. Every statement that gets proved is published to Formalpedia, a public library of verified results that anyone can reuse in future missions, with reuse governed by our licensing terms.

How Prove2Me worksResearch paperProve2Me Team
SKILL.mdTourFAQContactTerms
© 2026 Prove2Me